发表机构
University of Pittsburgh; New York University; Medical College of Wisconsin（匹兹堡大学; 纽约大学; 威斯康星医学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出覆盖导向修订（CDR）框架，利用知识图谱识别并引导大语言模型补全环境AI生成的临床笔记中缺失的医学信息，在两个数据集上显著提升内容召回率。
AI 中文摘要
环境人工智能在医疗保健领域的应用日益广泛，它能够从患者与临床医生的对话中自动生成临床笔记，有望大幅减轻临床医生的文书负担。然而，生成的笔记可能会遗漏就诊期间讨论的临床相关信息，造成信息缺口，进而影响后续护理。从就诊记录文本构建的知识图谱（KGs）可以提供所讨论内容的结构化表示，并能够系统地识别生成的笔记中缺失的、对患者护理至关重要的信息。在本研究中，我们引入了覆盖导向修订（CDR），这是一种与模型无关的框架，它从就诊记录文本中构建知识图谱，识别初始生成的笔记中缺失的医学概念，并引导大型语言模型（LLMs）恢复缺失的信息，而无需修改底层的笔记生成系统。我们在两个数据集上评估了CDR：1）Pitt-Bench，一个包含康复会话的本地数据集；2）ACI-Bench，一个用于临床笔记生成基准测试的公共数据集。我们测试了环境人工智能系统中广泛使用的四种底层LLM。结果表明，CDR在所有评估条件下均持续提高了内容召回率。我们的研究为提高环境人工智能生成的临床文档的完整性提供了一种实用方法。
英文摘要
Ambient AI is increasingly adopted in healthcare to automatically generate clinical notes from patient-clinician conversations, with the potential to substantially reduce clinician documentation burden. However, generated notes may omit clinically relevant information discussed during the encounter, creating information gaps that can affect downstream care. Knowledge graphs (KGs) constructed from encounter transcripts can provide a structured representation of what was discussed and enable systematic identification of missing information from generated notes that are critical for patient care. In this study, we introduce Coverage-Directed Revision (CDR), a model-agnostic framework that constructs a KG from the encounter transcript, identifies medical concepts absent from an initially generated note, and directs large language models (LLMs) to restore the missing information without modifying the underlying note-generation system. We evaluate CDR on two datasets: 1) Pitt-Bench, a local dataset comprising rehabilitation sessions, and 2) ACI-Bench, a public dataset for benchmarking clinical note generation. We tested four underlying LLMs widely used in ambient AI systems. The results show that CDR consistently improves content recall across all evaluated conditions. Our study provides a practical approach for improving the completeness of ambient AI-generated clinical documentation.
